academic-research
Skill1 starsChanged 50 days agoMITView on GitHub
Find, read and summarise peer-reviewed papers and build a short cited literature review. Use when the user asks what the research says, wants papers on a topic, needs a literature review, or asks to evaluate a study's methods.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- ViewWay/academic-research-skilltheir own version, first seen May 19, 2026
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
- fabioc-aloha/alex-cognitive-architecturetheir own version, first seen Apr 26, 2026
- hint-shu/deep-researchtheir own version, first seen Apr 17, 2026
- tdimino/claude-code-minoantheir own version, first seen Apr 16, 2026
- voidful/academic-skillstheir own version, first seen Mar 23, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- voidful/academic-skills★ 126same name
- tdimino/claude-code-minoan★ 41same name
- sergeeey/Claude-cod-top-2026★ 9same name
- orhoncan/oneshot-academic-research-skill★ 8same name
- hint-shu/deep-research★ 4same name
- ViewWay/academic-research-skill★ 4same name
- fabioc-aloha/alex-cognitive-architecture★ 0same name
- romanmesicek/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- codebase-auditSkill
- code-documentationSkill
- code-reviewSkill
- competitive-analysisSkill
- data-analysisSkill
- email-assistantSkill
- fullstack-dev-teamSkill
- github-integrationSkill
- market-researchSkill
- pdf-analysisSkill
- research-paperSkill
- sql-analysisSkill
- ui-ux-designSkill
- web-researchSkill
- web-searchSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Search scholarly sources, screen papers by relevance and quality, and synthesise them into a literature review with proper citations and an …
- Distinctive: line 51
Never invents citations — if a reference can't be found again, it is dropped.
- Distinctive: line 52
Not a substitute for a formal systematic review.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Academic Research
Overview
Search scholarly sources, screen papers by relevance and quality, and synthesise them into a literature review with proper citations and an honest read of the evidence.
When to Use
- "What does the research say about…", "find papers on…", "literature review of…"
- Evaluating a specific study ("is this paper any good?").
- Preparing background for a thesis, grant or technical decision.
Usage
- Scope. Define the question, the time window and inclusion criteria (study type, population, field). Confirm with the user if unclear.
- Search scholarly indexes (Google Scholar, Semantic Scholar, PubMed, arXiv, SSRN — whichever fit the field). Use 2–3 query variants plus the key authors' names once you find them.
- Screen titles and abstracts. Keep 5–15 papers. Prefer systematic reviews and meta-analyses, then large or well-controlled studies.
- Read each kept paper's abstract, methods and results. For each record: design, sample size, main finding, effect size, limitations, funding/conflicts.
- Synthesise by theme, not paper by paper. Note where findings agree, conflict, or where evidence is thin.
- Output:
- One-paragraph summary of the state of evidence.
- Themed sections with in-text citations
(Author, Year). - A table: paper · design · n · finding · quality note.
- Reference list in the style the user asks for (default APA).
- Mark preprints as not peer-reviewed.
Examples
Prompt: "Summarise the research on spaced repetition for learning programming."
The agent finds reviews on the spacing effect, narrows to studies in computing education, builds a table of 8 papers, and concludes that evidence is strong for factual recall but limited for problem-solving skills.
Limitations
- Full text may be paywalled; the agent says when it only read the abstract.
- Never invents citations — if a reference can't be found again, it is dropped.
- Not a substitute for a formal systematic review.
Changelog
- 1.2.0 — Preprints are now flagged explicitly; added quality-note column.
- 1.1.0 — Themed synthesis instead of per-paper summaries.
- 1.0.0 — Initial release.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.